Last refreshed 2026-05-19. Next refresh: weekly.
Why use Codestral Mamba 7B on NVIDIA NIM?
NVIDIA NIM offers Codestral Mamba 7B with competitive pricing. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.
Input / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: mistralai/mamba-codestral-7b-v0.1Model ID
mistralai/mamba-codestral-7b-v0.1Request example
Curated snippets for this provider are not sourced yet. Use NVIDIA NIM documentation with model ID
mistralai/mamba-codestral-7b-v0.1.Gotchas
- Use provider model ID "mistralai/mamba-codestral-7b-v0.1", not the LLMReference slug "codestral-mamba-7b".
Pricing
| Type | Rate |
|---|---|
| GPU Hour Rate | $1.00/GPU·hr |
| GPU Config | 1xH100 |
Capabilities
No model capability flags are currently sourced.
About Codestral Mamba 7B
Codestral Mamba 7B is MistralAI's Codestral model. It offers a 256K-token context window.
FAQ
What is the context window for Codestral Mamba 7B on NVIDIA NIM?
Codestral Mamba 7B supports a 256k token context window on NVIDIA NIM.
What API model ID do I use for Codestral Mamba 7B on NVIDIA NIM?
Use the model ID mistralai/mamba-codestral-7b-v0.1 when calling NVIDIA NIM's API.
Who created Codestral Mamba 7B?
Codestral Mamba 7B was created by MistralAI as part of the Codestral model family.
Is Codestral Mamba 7B open source?
Codestral Mamba 7B has open weights under Mistral License according to the seed data, but that does not necessarily mean an OSI-approved open-source license.
Model Specs
Released2024-07-16
Parameters7B
Context256k
ArchitectureDecoder Only